© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82873
    Prev
    Next
    INDEX
    Explanations

    event listeners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     APPE
    -0.84
     BENEFITS
    -0.79
     dando
    -0.73
    Invo
    -0.72
     dwa
    -0.71
     prazo
    -0.71
     klas
    -0.71
     urod
    -0.71
    <0xC8>
    -0.70
    стояние
    -0.70
    POSITIVE LOGITS
     pemeriksaan
    0.82
    close
    0.81
     phénomènes
    0.80
    semver
    0.79
     before
    0.77
    error
    0.77
     listener
    0.75
     témoignages
    0.75
    ūra
    0.75
     did
    0.74
    Activations Density 0.022%

    No Known Activations